BACKGROUND AND PURPOSE: Atypical clinical presentations of spontaneous intracranial hypotension include obtundation, memory deficits, dementia with frontotemporal features, parkinsonism, and ataxia_. The purpose of this study was to compare clinical and imaging features of spontaneous intracranial hypotension with typical-versus-atypical presentations. MATERIALS AND METHODS: Clinical records and neuroimaging of patients with spontaneous intracranial hypotension from September 2005 to August 2014 were retrospectively evaluated. Patients with classic spontaneous intracranial hypotension (n = 33; mean age, 41.7 ± 14.3 years) were compared with those with intracranial hypotension with atypical clinical presentation (n = 8; mean age, 55.9 ± 14.1 years) and 36 controls (mean age, 41.4 ± 11.2 years). RESULTS: Patients with atypical spontaneous intracranial hypotension were older than those with classic spontaneous intracranial hypotension (55.9 ± 14.1 years versus 41.7 ± 14.3 years; P = .018). Symptom duration was shorter in classic compared with atypical spontaneous intracranial hypotension (3.78 ± 7.18 months versus 21.93 ± 18.43 months; P = .015). There was no significant difference in dural enhancement, subdural hematomas, or cerebellar tonsil herniation. Patients with atypical spontaneous intracranial hypotension had significantly more elongated anteroposterior midbrain diameter compared with those with classic spontaneous intracranial hypotension (33.6 ± 2.9 mm versus 27.3 ± 2.9 mm; P < .001) and shortened pontomammillary distance (2.8 ± 1 mm versus 5.15 ± 1.5 mm; P < .001). Patients with atypical spontaneous intracranial hypotension were less likely to become symptom-free, regardless of treatment, compared with those with classic spontaneous intracranial hypotension (χ² = 13.99, P < .001). CONCLUSIONS: In this sample of 8 patients, atypical spontaneous intracranial hypotension was a more chronic syndrome compared with classic spontaneous intracranial hypotension, with more severe brain sagging, lower rates of clinical response, and frequent relapses. Awareness of atypical presentations of spontaneous intracranial hypotension is paramount.

Purpose: The Response Assessment in Neuro-Oncology (RANO) criteria for lower-grade gliomas (LGGs) define tumor progression as ≥25% change in the T2/FLAIR signal area based on an operator’s discretion of the perpendicular diameter of the largest tumor cross-section. Potential sources of error include acquisition inconsistency of 2D slices, operator selection variabilities in both representative tumor cross-section and measurement line locations, and the inability to quantify infiltrative tumor margins and satellite lesions. Our goal was to assess the accuracy and reproducibility of RANO in LG. Materials and Methods: A total of 651 FLAIR MRIs from 63 participants with LGGs were retrospectively analyzed by three blinded attending physicians and three blinded resident trainees using RANO criteria, 2D visual assessment, and computer-assisted 3D volumetric assessment. Results: RANO product measurements had poor-to-moderate inter-operator reproducibility (r² = 0.28–0.82; coefficient of variance (CV) = 44–110%; mean percent difference (diff) = 0.4–46.8%) and moderate-to-excellent intra-operator reproducibility (r² = 0.71–0.88; CV = 31–58%; diff = 0.3–23.9%). When compared to 2D visual ground truth, the accuracy of RANO compared to previous and baseline scans was 66.7% and 65.1%, with an area under the ROC curve (AUC) of 0.67 and 0.66, respectively. When comparing to volumetric ground truth, the accuracy of RANO compared to previous and baseline scans was 21.0% and 56.5%, with an AUC of 0.39 and 0.55, respectively. The median time delay at diagnosis was greater for false negative cases than for false positive cases for the RANO assessment compared to previous (2.05 > 0.50 years, p = 0.003) and baseline scans (1.08 > 0.50 years, p = 0.02). Conclusion: RANO-based assessment of LGGs has moderate reproducibility and poor accuracy when compared to either visual or volumetric ground truths.

Patients diagnosed with glioblastoma multiforme (GBM) continue to face a dire prognosis. Developing accurate and efficient contouring methods is crucial, as they can significantly advance both clinical practice and research. This study evaluates the AI models developed by MRIMath© for GBM T1c and fluid attenuation inversion recovery (FLAIR) images by comparing their contours to those of three neuro-radiologists using a smart manual contouring platform. The mean overall Sørensen–Dice Similarity Coefficient metric score (DSC) for the post-contrast T1 (T1c) AI was 95%, with a 95% confidence interval (CI) of 93% to 96%, closely aligning with the radiologists’ scores. For true positive T1c images, AI segmentation achieved a mean DSC of 81% compared to radiologists’ ranging from 80% to 86%. Sensitivity and specificity for T1c AI were 91.6% and 97.5%, respectively. The FLAIR AI exhibited a mean DSC of 90% with a 95% CI interval of 87% to 92%, comparable to the radiologists’ scores. It also achieved a mean DSC of 78% for true positive FLAIR slices versus radiologists’ scores of 75% to 83% and recorded a median sensitivity and specificity of 92.1% and 96.1%, respectively. The T1C and FLAIR AI models produced mean Hausdorff distances (<5 mm), volume measurements, kappa scores, and Bland–Altman differences that align closely with those measured by radiologists. Moreover, the inter-user variability between radiologists using the smart manual contouring platform was under 5% for T1c and under 10% for FLAIR images. These results underscore the MRIMath© platform’s low inter-user variability and the high accuracy of its T1c and FLAIR AI models.

Low-grade gliomas (LGG) invade the brains of young and productive adults leading to significant neurological morbid-ity. Mutations in the isocitrate dehydrogenase (IDH) gene are very common in LGG. Because IDH1 inhibitors are ef-fective in the treatment of LGG, early detection of growth is critical to initiating therapy without delay. This retrospec-tive observational study evaluates the ability of AI-assisted volumetric analysis to correctly detect tumor growth in lon-gitudinal studies of LGG as compared to the standard clinical method of visual inspection by radiologists. The study includes 63 participants categorized into clinical progression (n = 34), clinically stable (n=22), and negative control groups (n = 7). The dates of detection of tumor growth by visual inspection were gathered from radiological reports. Longitudinal tumor volumes were calculated from automated segmentations by the MRIMath FLAIR AI. Golden truths were obtained by physician review using the MRIMath Smart manual contouring system. Growth by significant shifts in tumor volumes was detected by using the statistical method of online change-of-point method. Our results demonstrate that in the clinical progression group, automatic AI segmentation followed by human review detected tu-mor growth at a median of 21 months earlier than visual inspection. In the clinically stable group, AI with human re-view identified growth in 13/22 cases at a median of 23 months earlier than the last MRI. AI without human review generated similar results but with a 25% false positive and an 8.33% false negative rate. The median time spent by physicians in reviewing, revising, and approving the AI segmentations is 2 minutes. These findings highlight the clin-ical potential of AI-assisted volumetric analysis followed by physician oversight for the timely detection of tumor pro-gression in LGG patients.

Glioblastomas (GBM) grow rapidly and infiltrate the cerebral parenchyma, leading to significant neurological morbidity and mortality. Early detection of tumor growth promotes early therapeutic interventions that delay neurological progression and possibly prolong survival times. This retrospective observational study evaluates the ability of AI-assisted volumetric analysis to correctly detect tumor progression in longitudinal studies of newly diagnosed GBM, compared to the standard clinical method of visual inspection by radiologists and neuro-oncologists. Fifteen of 56 patients met the inclusion and exclusion criteria. The dates of tumor progression were gathered from clinical reports. Longitudinal tumor volumes were calculated from automated segmentations by the MRIMath T1c AI followed by physician review using the MRIMath Smart manual contouring system. Growth by significant shifts in tumor volumes was detected by using the statistical method of the online change-of-point method. Our results demonstrate that automatic AI segmentation followed by human review detects tumor progression earlier than clinical notes in 4/15 patients at a median of 105 days. Furthermore, the longitudinal AI-measured volumes validated two cases of pseudoprogression as evidenced by subsequent volume stability. This study emphasizes the enhanced diagnostic accuracy achieved by incorporating volumetric data analysis into clinical decision-making. This can be accomplished by integrating efficient AI-powered segmentation and a streamlined human review system into the clinical workflow.